Now live — presented at London Bioinformatics Meetup, Feb 2026

The first bioinformatics-native
AI agent skill library

Every figure in your paper should be one command away from reproduction. Local-first. Privacy-focused. Reproducible. Built on OpenClaw.

⭐ View on GitHub Submit a Skill
bioinformaticsgenomicsreproducibilitypopulation-geneticsequityai-agentslocal-firstopenclaw

NutriGx Advisor — community-contributed skill running locally on raw genetic data

The Problem
Reproducing bioinformatics analyses is broken
# Without ClawBio
$ git clone repo && cd repo
# Wrong Python version...
# Reference data link is dead...
# Paths hardcoded to /home/jsmith/data/
# Email first author. Wait 3 weeks.
# Give up.
  • ✗ Dependency hell & broken environments
  • ✗ Dead links to reference data
  • ✗ Hardcoded paths & missing configs
  • ✗ AI hallucinates star alleles & outdated guidelines
  • ✗ No audit trail, no checksums
# With ClawBio
$ python ancestry_pca.py --demo --output fig3

✓ Figure 3 reproduced.
✓ Identical. SHA-256 verified.
✓ 30 seconds.

# Or with natural language:
$ openclaw "Profile my pharmacogenes"

Every skill exports commands.sh, environment.yml, and SHA-256 checksums — anyone can reproduce without the agent.

Why ClawBio
Domain expertise, frozen into code

ChatGPT and Claude are smart generalists. ClawBio skills are domain experts' proven pipelines — executed correctly every time.

🏠
Local-first
Your genomic data never leaves your laptop. No cloud uploads, no data exfiltration. Full privacy by design.
🔁
Reproducible
Every analysis exports a reproducibility bundle — commands, environment, and SHA-256 checksums. Reproduce without the agent.
🧩
Modular
Each skill is a self-contained directory (SKILL.md + Python scripts) that plugs into the orchestrator — or runs standalone.
⚖️
MIT Licensed
Open-source, free, community-driven. Clone it, run it, build a skill, submit a PR.
🌍
Equity-aware
Built-in support for underrepresented populations. HEIM diversity metrics baked into the roadmap.
🤖
Built on OpenClaw
Powered by OpenClaw (180k+ GitHub stars) — the agent platform that routes natural language to the right specialist skill.
Skills Library
7 skills — live now

Each skill includes demo data so you can try it immediately without your own files.

🧭 Bio Orchestrator
Routes bioinformatics requests to the right specialist skill by file type and keywords.
MVP
💊 PharmGx Reporter
Pharmacogenomic report from 23andMe/AncestryDNA: 12 genes, 51 drugs, CPIC guidelines. Runs in <1 second.
MVP
🌍 Ancestry PCA
PCA decomposition vs SGDP reference panel (345 samples, 164 global populations). Publication-quality figures.
MVP
📚 Semantic Similarity
Semantic Isolation Index for 175 GBD diseases from 13.1M PubMed abstracts using PubMedBERT embeddings.
MVP
⚖️ Equity Scorer
HEIM diversity metrics from VCF/ancestry data. Heterozygosity, FST, PCA, and composite equity scores.
MVP
🥗 NutriGx Advisor
Nutrigenomics report: 40 SNPs, 13 nutrient domains, personalised dietary recommendations. Community-contributed.
MVP
🧬 Metagenomics Profiler
Microbial community profiling with Kraken2/Bracken. Alpha diversity, taxonomic composition, abundance plots.
MVP
🧬 VCF Annotator
Variant annotation with VEP, ClinVar, gnomAD + ancestry context.
Planned
📄 Lit Synthesizer
PubMed/bioRxiv search with LLM summarisation and citation graphs.
Planned
🔬 scRNA Orchestrator
Scanpy automation: QC, clustering, DE analysis, visualisation.
Planned
Community
Wanted: skills from the community

If you work with genomics, proteomics, metabolomics, imaging, or clinical data — wrap your pipeline as a skill.

claw-gwas
PLINK/REGENIE automation — Statistical genetics
claw-metagenomics
Kraken2/MetaPhlAn wrapper — Microbiome
claw-acmg
Clinical variant classification — Clinical genomics
claw-pathway
GO/KEGG enrichment — Functional genomics
claw-phylogenetics
IQ-TREE/RAxML automation — Evolutionary biology
claw-proteomics
MaxQuant/DIA-NN — Proteomics
claw-spatial
Visium/MERFISH — Spatial transcriptomics
+
Your skill here
📖 Read the contribution guide

Get started in 30 seconds

Install a skill, run with natural language or directly — every skill includes demo data.

# Install a skill
openclaw install skills/pharmgx-reporter

# Run with natural language
openclaw "Profile my pharmacogenes"

# Or run directly
python pharmgx_reporter.py --input demo --output report
⭐ Star on GitHub 📄 Full documentation